Papers

New on arXiv

Sun 27 Apr 2025

124 papers

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and ProspectsLLM reasoning → Knowledge- and tool-augmented reasoning
Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic ForgettingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented GenerationRetrieval-augmented generation → Conversational and speech RAG
SAGA: A Security Architecture for Governing AI Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single ImageDiffusion models → Robustness, privacy and adversarial aspects +1
Swapped Logit Distillation via Bi-level Teacher AlignmentKnowledge distillation → General knowledge distillation methods
Adaptive Helpfulness-Harmlessness Alignment with Preference VectorsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
PlanetServe: A Decentralized, Scalable, and Privacy-Preserving Overlay for Democratizing Large Language Model ServingEfficient LLM inference and serving → Serving systems and request scheduling
HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural NetworksDeep reinforcement learning methods → Deep RL algorithms and representations
O(1/k) Finite-Time Bound for Non-Linear Two-Time-Scale Stochastic ApproximationDeep reinforcement learning methods → RL theory and sample complexity
Contextual Online Uncertainty-Aware Preference Learning for Human FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Unified Multi-Task Learning & Model Fusion for Efficient Language Model GuardrailingLLM safety and security → Safety alignment, refusal and guardrails
AndroidGen: Building an Android Language Agent under Data ScarcityLLM agents and tool use → GUI and mobile agents
Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function CallingLLM agents and tool use → Tool learning and function calling +1
Anyprefer: An Agentic Framework for Preference Data SynthesisLLM agents and tool use → Reinforcement learning for LLM agents +1
The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework ApproachLLM reasoning → Reasoning benchmarks and evaluation
WuNeng: Hybrid State with AttentionEfficient LLM inference and serving → KV cache optimization
Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosDiffusion models → Audio, speech and music
SPC: Evolving Self-Play Critic via Adversarial Games for LLM ReasoningLLM reasoning → Reasoning for agents, planning and code +1
ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware DevelopmentLLM reasoning → Reasoning for agents, planning and code
BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented GenerationRetrieval-augmented generation → Privacy and security of RAG
Efficient Reasoning for LLMs through Speculative Chain-of-ThoughtLLM reasoning → Test-time compute and efficient thinking
CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography ChallengesLLM reasoning → Reasoning for agents, planning and code
Learning to Drive from a World ModelWorld models → World models for autonomous driving +1
Supervised machine learning based signal demodulation in chaotic communications
Low-Complexity CNN-Based Classification of Electroneurographic Signals
Evolutionary Optimization for the Classification of Small Molecules Regulating the Circadian Rhythm Period: A Reliable Assessment
Transcending Dimensions using Generative AI: Real-Time 3D Model Generation in Augmented Reality
Selecting the Right LLM for eGov Explanations
Supervised Pretraining for Material Property Prediction
Attention to Detail: Fine-Scale Feature Preservation-Oriented Geometric Pre-training for AI-Driven Surrogate Modeling
Personalized Artificial General Intelligence (AGI) via Neuroscience-Inspired Continuous Learning Systems
Electricity Cost Minimization for Multi-Workflow Allocation in Geo-Distributed Data Centers
An on-production high-resolution longitudinal neonatal fingerprint database in Brazil
Heterogeneous network drug-target interaction prediction model based on graph wavelet transform and multi-level contrastive learning
HyboWaveNet: Hyperbolic Graph Neural Networks with Multi-Scale Wavelet Transform for Protein-Protein Interaction Prediction
LLMs for Engineering: Teaching Models to Design High Powered Rockets
Ridge partial correlation screening for ultrahigh-dimensional data
Bi-directional Model Cascading with Proxy Confidence
HumMorph: Generalized Dynamic Human Neural Fields from Few Views
From Inductive to Deductive: LLMs-Based Qualitative Data Analysis in Requirements Engineering
From Distance to Direction: Structure-aware Label-specific Feature Fusion for Label Distribution Learning
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Composable and adaptive design of machine learning interatomic potentials guided by Fisher-information analysis
Mitigating Bias in Facial Recognition Systems: Centroid Fairness Loss Optimization
Low-Rank Adaptive Structural Priors for Generalizable Diabetic Retinopathy Grading
MERA: Multimodal and Multiscale Self-Explanatory Model with Considerably Reduced Annotation for Lung Nodule Diagnosis
Metric Similarity and Manifold Learning of Circular Dichroism Spectra of Proteins
Neurosymbolic Association Rule Mining from Tabular Data
Flow Along the K-Amplitude for Generative Modeling
The Double Descent Behavior in Two Layer Neural Network for Binary Classification
Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
PolyTouch: A Robust Multi-Modal Tactile Sensor for Contact-rich Manipulation Using Tactile-Diffusion Policies
Explanatory Summarization with Discourse-Driven Planning
Enhancing seeding efficiency using a computer vision system to monitor furrow quality in real-time
DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding
NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI
Logic-Based Artificial Intelligence Algorithms Supporting Categorical Semantics
BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese
Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography
FusionNet: Multi-model Linear Fusion Framework for Low-light Image Enhancement
Marine Snow Removal Using Internally Generated Pseudo Ground Truth
Ethical Challenges of Using Artificial Intelligence in Judiciary
Optimal Hyperspectral Undersampling Strategy for Satellite Imaging
Balancing Creativity and Automation: The Influence of AI on Modern Film Production and Dissemination
TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks
Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detection
VI3NR: Variance Informed Initialization for Implicit Neural Representations
VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?
OpenFusion++: An Open-vocabulary Real-time Scene Understanding System
Navigating AI Policy Landscapes: Insights into Human Rights Considerations Across IEEE Regions
Rendering Anywhere You See: Renderability Field-guided Gaussian Splatting
Convergence Properties of Natural Gradient Descent for Minimizing KL Divergence
OPAL: Visibility-aware LiDAR-to-OpenStreetMap Place Recognition via Adaptive Radial Fusion
LM-MCVT: A Lightweight Multi-modal Multi-view Convolutional-Vision Transformer Approach for 3D Object Recognition
Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers
Quantitative evaluation of brain-inspired vision sensors in high-speed robotic perception
ODExAI: A Comprehensive Object Detection Explainable AI Evaluation
Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
The effect of the number of parameters and the number of local feature patches on loss landscapes in distributed quantum neural networks
Test Set Sizing for the Ridge Regression
Unsupervised 2D-3D lifting of non-rigid objects using local constraints
CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis
CapsFake: A Multimodal Capsule Network for Detecting Instruction-Guided Deepfakes
FlexPara: Flexible Neural Surface Parameterization
Dynamic Embedded Topic Models: properties and recommendations based on diverse corpora
Improving Generalization in MRI-Based Deep Learning Models for Total Knee Replacement Prediction
Leveraging Modified Ex Situ Tomography Data for Segmentation of In Situ Synchrotron X-Ray Computed Tomography
Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integration
Adaptive Dual-domain Learning for Underwater Image Enhancement
Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements
Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
Hierarchical Attention Generates Better Proofs
LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition
A Design Framework for operationalizing Trustworthy Artificial Intelligence in Healthcare: Requirements, Tradeoffs and Challenges for its Clinical Adoption
Newton-Puiseux Analysis for Interpretability and Calibration of Complex-Valued Neural Networks
CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
RadioFormer: A Multiple-Granularity Radio Map Estimation Transformer with 1textpertenthousand Spatial Sampling

All 124